Few-Shot Class-Incremental Learning
39 papers with code • 3 benchmarks • 3 datasets
Benchmarks
These leaderboards are used to track progress in Few-Shot Class-Incremental Learning
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
CIFAR-100
CUB-200-2011
mini-Imagenet
Most implemented papers
Graph Few-shot Class-incremental Learning
The ability to incrementally learn new classes is vital to all real-world artificial intelligence systems.
Forward Compatible Few-Shot Class-Incremental Learning
zhoudw-zdw/cvpr22-fact
•
•
CVPR 2022
Forward compatibility requires future new classes to be easily incorporated into the current model based on the current stage data, and we seek to realize it by reserving embedding space for future new classes.
Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks
In this work, we propose a new paradigm for FSCIL based on meta-learning by LearnIng Multi-phase Incremental Tasks (LIMIT), which synthesizes fake FSCIL tasks from the base dataset.
Geometer: Graph Few-Shot Class-Incremental Learning via Prototype Representation
Instead of replacing and retraining the fully connected neural network classifer, Geometer predicts the label of a node by finding the nearest class prototype.
Few-shot Class-incremental Learning for 3D Point Cloud Objects
Few-shot class-incremental learning (FSCIL) aims to incrementally fine-tune a model (trained on base classes) for a novel set of classes using a few examples without forgetting the previous training.
Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replay
liuh127/FSCIL-via-Entropy-regularized-DF-Replay
•
•
In this paper, we show through empirical results that adopting the data replay is surprisingly favorable.
Few-Shot Class-Incremental Learning from an Open-Set Perspective
The continual appearance of new objects in the visual world poses considerable challenges for current deep learning methods in real-world deployments.
Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigation
zoilsen/clom
•
•
Few-shot class-incremental learning (FSCIL) is designed to incrementally recognize novel classes with only few training samples after the (pre-)training on base classes with sufficient samples, which focuses on both base-class performance and novel-class generalization.
GKEAL: Gaussian Kernel Embedded Analytic Learning for Few-Shot Class Incremental Task
ZHUANGHP/Analytic-continual-learning
•
•
CVPR 2023
In this paper, we approach the FSCIL by adopting analytic learning, a technique that converts network training into linear problems.
Few-Shot Class-Incremental Learning via Class-Aware Bilateral Distillation
linglanzhao/bidistfscil
•
•
CVPR 2023
While knowledge distillation, a prevailing technique in CIL, can alleviate the catastrophic forgetting of older classes by regularizing outputs between current and previous model, it fails to consider the overfitting risk of novel classes in FSCIL.
